© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    operator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zate
    -0.42
    sillon
    -0.40
    #![
    -0.40
    enegger
    -0.40
     Ravens
    -0.37
    retum
    -0.37
    úrate
    -0.37
    ogramm
    -0.36
    Mu
    -0.36
    AudioSource
    -0.36
    POSITIVE LOGITS
     חיצוניים
    0.84
    DoubleQuotes
    0.81
    IsContent
    0.79
     مشين
    0.79
    AnchorStyles
    0.78
    цездатний
    0.76
     ligiloj
    0.74
    BeginContext
    0.73
    Hentet
    0.73
     ویکی‌پدیای
    0.71
    Activations Density 0.017%

    No Known Activations